Clinical phenogroups are more effective than left ventricular ejection fraction categories in stratifying heart failure outcomes

ConclusionAmong patients hospitalized for HF, clinical phenotypes generated by unsupervised machine learning provided greater prognostic information for a composite of clinical endpoints at 6 and 12 months compared with LVEF‐based categories.Trial Registration:ClinicalTrials.gov Identifier: NCT02112227

https://onlinelibrary.wiley.com/doi/10.1002/ehf2.13344?af=R

Source: ESC Heart Failure - May 2, 2021 Category: Cardiology Authors: Andreas B. Gevaert, Semra Tibebu, Mamas A. Mamas, Neal G. Ravindra, Shun Fu Lee, Tariq Ahmad, Dennis T. Ko, James L. Januzzi, Harriette G.C. Van Spall Tags: Original Research Article Source Type: research